crystallize
Skill0 starsChanged 6 months agoMITView on GitHub
【全局技能】深度复盘当前对话的解题路径、失败尝试与影响范围，追加沉淀到当前项目的 docs/THOUGHTS.md 中。
2 other projects use a version of this.
Adopted by
Most recently taken up by
- avelikiy/great_ctotheir own version, first seen Sep 5, 2026
- ratacat/ratacats-skillstheir own version, first seen Jul 4, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- avelikiy/great_cto★ 112same name
- ratacat/ratacats-skills★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- multi-agent-scaffoldSkill
The file
Files
终极思路沉淀智能体技能 (Global Crystallize Thought Process)
当你（Claude）发现解决了一个复杂的代码问题，或者用户在任意项目中主动输入了 /crystallize 时，请触发本技能。
执行步骤：
- 精准分类判定：
从以下标签中选择最契合的 1-2个：
[Bug修复],[性能优化],[架构设计],[环境配置],[工程化],[AI工作流] - 多维提取与格式化：
严格按照以下 Markdown
<details>模板组织内容。务必提取出技术栈关键词、复用价值，以及真实的失败尝试。 - 目录与文件准备 (全局环境关键步骤)：
由于你运行在各种不同的项目中，请务必先确保目录存在：
mkdir -p docs若创建失败（如权限不足），向用户报告具体原因并中止。 - 持久化追加：
将生成的 Markdown 文本**追加（Append）**到当前项目根目录的
docs/THOUGHTS.md文件末尾（用两行空行隔开，绝对不可覆盖历史记录）。 - VS Code 联动：
写入完成后，在终端执行
code -r docs/THOUGHTS.md唤起用户的编辑器。
写入模板标准
[YYYY-MM-DD] 【类型标签】一句话概括核心问题或变更
核心标签: #分类标签 关键词: #技术栈1 #技术栈2 复用价值: ⭐️⭐️⭐️⭐️☆
<details>
<summary> 点击展开深度技术复盘（包含失败尝试与影响范围）</summary>问题现象 & 影响范围
- 背景现象：简述遇到了什么 Bug、报错信息或核心需求。
- 波及模块：修改了哪些模块？是否涉及破坏性变更或影响生产环境？
❌ 失败尝试 (Rejected Solutions)
- 尝试 1：[做了什么尝试] -> 失败原因：[为什么无效/误判] (注：如果一次性成功，此项可写"无")
根本原因 (Root Cause)
- 底层机制：导致问题的核心逻辑、协议限制或框架机制是什么？
最终有效解法
- 核心路径：最终是如何彻底修复或实现的。
- 关键代码/命令：
# 留存最关键的配置命令、diff 或修复代码
经验教训 (Lessons Learned)
- 核心认知：这次解决过程中获得的关键洞察。
- 可复用模式：类似场景可直接套用本解法。
</details>约束
- 只输出符合上述模板的内容，禁止在模板之外掺杂闲聊、自我评价或无关对话片段。
- 若用户未提供足够信息（如不知道问题分类），向用户追问关键细节后再生成记录。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.